init: RAG 知识库服务初始提交

- 后端 API(Flask + Gunicorn)
- RAG 引擎(混合检索 + 云端 Reranker + 引用溯源)
- 文档解析(MinerU + 多格式支持)
- Docker 生产部署配置
- 排除前端项目、敏感配置、模型文件
This commit is contained in:
lacerate551
2026-06-04 17:35:27 +08:00
commit 100d1a06eb
158 changed files with 64534 additions and 0 deletions

27
parsers/txt_parser.py Normal file
View File

@@ -0,0 +1,27 @@
"""
TXT 文本解析器
简单的文本文件读取,支持 UTF-8 和 GBK 编码自动检测。
"""
import logging
logger = logging.getLogger(__name__)
def extract_text_from_txt(filepath):
"""从TXT提取文本"""
try:
with open(filepath, 'r', encoding='utf-8') as f:
return f.read()
except UnicodeDecodeError:
# 尝试其他编码
try:
with open(filepath, 'r', encoding='gbk') as f:
return f.read()
except Exception as e:
logger.error(f"TXT解析错误 {filepath}: {e}")
return ""
except Exception as e:
print(f" TXT解析错误 {filepath}: {e}")
return ""